{"id":"https://openalex.org/W3113874423","doi":"https://doi.org/10.1109/uemcon51285.2020.9298159","title":"A Data Structure for Efficient File Deduplication in Cloud Storage","display_name":"A Data Structure for Efficient File Deduplication in Cloud Storage","publication_year":2020,"publication_date":"2020-10-28","ids":{"openalex":"https://openalex.org/W3113874423","doi":"https://doi.org/10.1109/uemcon51285.2020.9298159","mag":"3113874423"},"language":"en","primary_location":{"id":"doi:10.1109/uemcon51285.2020.9298159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon51285.2020.9298159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics &amp; Mobile Communication Conference (UEMCON)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057216347","display_name":"Bohui Wang","orcid":"https://orcid.org/0000-0003-1625-6548"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohui Wang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603408","display_name":"Hui Li","orcid":"https://orcid.org/0009-0003-2918-208X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022411883","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0003-0321-1383"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["Shenzhen SmartCity Technology, Development Group Co.,Ltd, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen SmartCity Technology, Development Group Co.,Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075677046","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0001-6813-7677"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080145446","display_name":"Huajun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajun Ma","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006725776","display_name":"Xin Xie","orcid":"https://orcid.org/0000-0002-8909-3105"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xie","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040700777","display_name":"Kaixuan Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Xing","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20376131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"0071","last_page":"0077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9407492876052856},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9358921051025391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8003234267234802},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7785518169403076},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6847656965255737},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6020346283912659},{"id":"https://openalex.org/keywords/cuckoo-search","display_name":"Cuckoo search","score":0.5333893895149231},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5015726089477539},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44645631313323975},{"id":"https://openalex.org/keywords/cloud-storage","display_name":"Cloud storage","score":0.4436124265193939},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4101823568344116},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2423054277896881},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20772293210029602},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19250404834747314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07209286093711853},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.06284093856811523}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9407492876052856},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9358921051025391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003234267234802},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7785518169403076},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6847656965255737},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6020346283912659},{"id":"https://openalex.org/C117241572","wikidata":"https://www.wikidata.org/wiki/Q5192379","display_name":"Cuckoo search","level":3,"score":0.5333893895149231},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5015726089477539},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44645631313323975},{"id":"https://openalex.org/C2777059624","wikidata":"https://www.wikidata.org/wiki/Q914359","display_name":"Cloud storage","level":3,"score":0.4436124265193939},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4101823568344116},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2423054277896881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20772293210029602},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19250404834747314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07209286093711853},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.06284093856811523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/uemcon51285.2020.9298159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon51285.2020.9298159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics &amp; Mobile Communication Conference (UEMCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313887","display_name":"ZTE Corporation","ror":"https://ror.org/00rjhhq63"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1639305476","https://openalex.org/W1967373117","https://openalex.org/W1981420413","https://openalex.org/W2001040824","https://openalex.org/W2050126243","https://openalex.org/W2102140417","https://openalex.org/W2123845384","https://openalex.org/W2126540423","https://openalex.org/W2142808699","https://openalex.org/W2346097572","https://openalex.org/W2350081975","https://openalex.org/W2769951192","https://openalex.org/W2792322951","https://openalex.org/W2806385177","https://openalex.org/W2883782645","https://openalex.org/W2911381130","https://openalex.org/W2912601938","https://openalex.org/W3005168640","https://openalex.org/W3081945319","https://openalex.org/W3085498367","https://openalex.org/W4236444653","https://openalex.org/W6675123562","https://openalex.org/W6684746344"],"related_works":["https://openalex.org/W3008420177","https://openalex.org/W2942719460","https://openalex.org/W2371981271","https://openalex.org/W3113874423","https://openalex.org/W2806950186","https://openalex.org/W4385661383","https://openalex.org/W1892538828","https://openalex.org/W2185747496","https://openalex.org/W3098509882","https://openalex.org/W3113693895"],"abstract_inverted_index":{"With":[0],"the":[1,25,63,81,88,92,116,121,134,139],"rapid":[2],"development":[3],"of":[4,30,91,129,143],"Internet,":[5],"massive":[6],"data":[7,49,74],"needs":[8],"to":[9,39,61,87,149,155],"be":[10,37],"stored,":[11],"bringing":[12],"a":[13],"significant":[14],"challenge":[15],"for":[16],"cloud":[17],"storage":[18],"systems.":[19],"It":[20],"is":[21,84,146],"notable":[22],"that":[23,35,138],"among":[24],"data,":[26],"there":[27],"are":[28],"plenty":[29],"duplicates":[31],"file":[32],"or":[33],"chunks":[34],"can":[36,113],"deduplicated":[38],"achieve":[40],"better":[41],"spatial":[42],"efficiency.":[43],"And":[44],"many":[45],"approximate":[46],"set":[47],"membership":[48],"structures,":[50],"such":[51],"as":[52,72],"Bloom":[53,157],"Filter(BF)":[54],"and":[55,80,123,131,133,153],"Cuckoo":[56,103,109,151],"Filter(CF),":[57],"have":[58],"been":[59],"used":[60],"accelerate":[62],"whole":[64],"deduplication":[65,93],"process.":[66],"However,":[67],"errors":[68],"will":[69],"inevitably":[70],"occur":[71],"these":[73,97],"structures":[75],"only":[76],"store":[77],"summary":[78],"information,":[79],"error":[82,117],"rate":[83,142],"directly":[85],"related":[86],"performance":[89],"bottleneck":[90],"system.":[94],"To":[95],"address":[96],"problems,":[98],"we":[99],"propose":[100],"an":[101],"advanced":[102],"Filter":[104,110,152],"named":[105],"Split":[106],"Position":[107],"Aware":[108],"(SPACF)":[111],"which":[112],"noticeably":[114],"decrease":[115],"rate.":[118],"We":[119],"implement":[120],"SPACF":[122,145],"compare":[124],"it":[125],"with":[126],"other":[127],"kinds":[128],"CFs":[130],"BF,":[132],"experiment":[135],"results":[136],"illustrate":[137],"false":[140],"positive":[141],"our":[144],"around":[147],"50%":[148],"Standard":[150],"10%":[154],"Counting":[156],"Filter.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
